Date: Tue, 29 Jun 1999 15:33:59 -0600 From: Wes Peters <wes@softweyr.com> To: "Daniel C. Sobral" <dcs@newsguy.com> Cc: Jonathan Walther <krooger@debian.org>, advocacy@FreeBSD.ORG Subject: Re: [Linux vs. NT, take 2.] Message-ID: <37793BC7.FAB4D452@softweyr.com> References: <Pine.LNX.3.96.990628194210.32578A-100000@lambdamoo.to> <3778E7A7.1F548BE@newsguy.com>
next in thread | previous in thread | raw e-mail | index | archive | help
"Daniel C. Sobral" wrote:
>
> Jonathan Walther wrote:
> >
> > The only damage was to Redhat. None of the Linux bigwigs participated.
> > Linus, Alan Cox, Jeremy Alison... none of them participated or endorsed the
> > benchmarks. Linux is pulling through this one pretty well. And the fact
> > that Mindcraft is still involved taints all results in the eyes of the
> > journalistic community. As well as the fact that Apache was what was
> > tested, not the faster web servers.
>
> Err... you should take a few pills of reality.
>
> The distinction between RedHat and linux distributions in general,
> the lack of "Linux bigwigs", the fact that Apache was used instead
> of other servers only affects the Linux community, which is not
> likely to change it's mind in first place. And the fact that
> Mindcraft is still involved doesn't taint the results anymore than
> the fact that Microsoft is involved, giving the steps taken to
> insure a fair process (quote me one non-Linux source saying the
> results a dubious!).
>
> This has a HUGE impact against Linux. And even an impact against
> other open source operating systems.
But most of the credible sources have been pointing out Linux faired
much better than in the original MindCraft tests, and that the
experimental Linux 2.3 kernel showed promise of being in the ballpark
with NT once again.
The capsule review in Network World pointed out this benchmark gave
the Linux developers some valuable performance data on WHERE to
improve their systems. It also pointed out that Solaris x86 whups
NT pretty handily without resorting to stupid stunts like putting
the guts of the FTP and HTTP servers into the kernel.
From the preliminary results reported here the other day, we have even
further to go to rise to these reported performance levels. Anyone
who is surprised by that hasn't been following the development of NT,
Solaris, or Linux very closely. The world is beginning to accept that
SMP servers are a good idea, and SMP is becoming "where it's at" in
the world of servers. If our SMP support lags far behind, we will
NOT be "where it's at" pretty quickly.
So, kudos and applause to the group working on better SMP scalability.
You guys are the future of FreeBSD. ;^)
--
"Where am I, and what am I doing in this handbasket?"
Wes Peters Softweyr LLC
http://www.softweyr.com/~softweyr wes@softweyr.com
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-advocacy" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?37793BC7.FAB4D452>